Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases referencing serious or critical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¿ãĥ«
    -0.16
     Crow
    -0.15
    สà¸Ļ
    -0.15
    adas
    -0.14
    elt
    -0.14
     lại
    -0.14
    ãĥģãĥ¥
    -0.14
    dub
    -0.13
    kelas
    -0.13
     Griffith
    -0.13
    POSITIVE LOGITS
     similarly
    0.18
    sian
    0.18
    exo
    0.16
    similar
    0.15
     pornos
    0.15
    irez
    0.14
    MethodInfo
    0.14
     similar
    0.14
    imilar
    0.14
    apot
    0.14
    Act Density 0.240%

    No Known Activations